© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 21056
    Prev
    Next
    INDEX
    Explanations

    events or actions that lead to conflict or resolution in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.20
    1:0.17
    2:0.07
    3:0.06
    4:0.04
    5:0.02
    6:0.06
    7:0.08
    8:0.03
    9:0.03
    10:0.14
    11:0.05
    Negative Logits
    imov
    -3.33
    utsche
    -3.30
     Uzbek
    -3.04
     Mellon
    -3.03
    ktop
    -3.02
     Cumm
    -2.99
     Kun
    -2.98
    assic
    -2.98
     DEBUG
    -2.85
    arthed
    -2.79
    POSITIVE LOGITS
     Rainbow
    9.68
    Rain
    7.40
     rainbow
    6.93
     Rain
    4.26
     Clouds
    3.95
     Siege
    3.61
     Discord
    3.53
     Prism
    3.52
    Pink
    3.50
     Pink
    3.45
    Activations Density 0.003%

    No Known Activations